Efficient Graph Cut Optimization for Shape From Focus

Christophe Ribal (1) , Nicolas Lermé (1) , Sylvie Le Hégarat-Mascle (1)

1 SATIE - Systèmes et Applications des Technologies de l'Information et de l'Energie

Shape From Focus refers to the problem of recovering the depth in every point of a scene from a set of differently focused 2D images. Recently, some authors stated this inverse problem in the variational framework and solved it by minimizing a non-convex functional. However, global optimality on the solution is not guaranted and evaluations are either application-specific or incomplete. To overcome these limits, we propose in this paper to globally and efficiently minimize a convex functional by decomposing it into a sequence of binary problems using graph cuts. To illustrate the genericity of such a decomposition-based approach, we investigate several decomposition strategies. Specifically, we focus on data-driven strategies suited to early reconstruction. We provide qualitative and quantitative evaluation on real popular datasets. According to classic statistics on error values, the proposed approach exhibits high performance and robustness against corruped data.

Mots clés: Shape From Focus; depth map estimation; graph cuts; multi-labels

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement du signal et de l'image [eess.SP]

Christophe Ribal, Nicolas Lermé, Sylvie Le Hégarat-Mascle. Efficient Graph Cut Optimization for Shape From Focus. Journal of Visual Communication and Image Representation, inPress. ⟨hal-01704877v1⟩